# Aspect Sentiment

> 한국어 텍스트의 측면별 감정·상태를 Claude가 직접 추출하는 ABSA(측면 기반 감정분석) 스킬입니다. "이 리뷰들 측면별 감정 뽑아줘", "상담 로그 측면 분석", "배송·품질 따로 긍부정 분류"처럼 말하면 됩니다. 무상태 단건 처리로 맥락 오염 0, 고정 JSON 스키마, 화자분리(고객 발화만), closed-set 분류체계로 집계 가능한 출력을 만듭니다.

## Facts
- Page: https://tashan.sh/capability/skill-itda-skills-aspect-sentiment
- tashan id: skill:itda-skills/aspect-sentiment
- Source: https://github.com/itda-skills/skills.pub
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 80.0
- Freshness: 95.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r aspect-sentiment ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.